scholarly journals Analysis of Health Insurance Big Data for Early Detection of Disabilities: Algorithm Development and Validation (Preprint)

2020 ◽  
Author(s):  
Seung-Hyun Jeong ◽  
Tae Rim Lee ◽  
Jung Bae Kang ◽  
Mun-Taek Choi
Keyword(s):  
Big Data ◽  
Health Insurance ◽  
Early Detection ◽  
Developmental Delays ◽  
Brain Lesion ◽  
Detection Model ◽  
Clinical Diagnoses ◽  
Significant Performance ◽  
Clinically Significant ◽  
Age Range

BACKGROUND Early detection of childhood developmental delays is very important for the treatment of disabilities. OBJECTIVE To investigate the possibility of detecting childhood developmental delays leading to disabilities before clinical registration by analyzing big data from a health insurance database. METHODS In this study, the data from children, individuals aged up to 13 years (n=2412), from the Sample Cohort 2.0 DB of the Korea National Health Insurance Service were organized by age range. Using 6 categories (having no disability, having a physical disability, having a brain lesion, having a visual impairment, having a hearing impairment, and having other conditions), features were selected in the order of importance with a tree-based model. We used multiple classification algorithms to find the best model for each age range. The earliest age range with clinically significant performance showed the age at which conditions can be detected early. RESULTS The disability detection model showed that it was possible to detect disabilities with significant accuracy even at the age of 4 years, about a year earlier than the mean diagnostic age of 4.99 years. CONCLUSIONS Using big data analysis, we discovered the possibility of detecting disabilities earlier than clinical diagnoses, which would allow us to take appropriate action to prevent disabilities.

scholarly journals Analysis of Health Insurance Big Data for Early Detection of Disabilities: Algorithm Development and Validation

10.2196/19679 ◽  
2020 ◽  
Vol 8 (11) ◽  
pp. e19679
Author(s):  
Seung-Hyun Jeong ◽  
Tae Rim Lee ◽  
Jung Bae Kang ◽  
Mun-Taek Choi
Keyword(s):  
Big Data ◽  
Health Insurance ◽  
Early Detection ◽  
Developmental Delays ◽  
Brain Lesion ◽  
Detection Model ◽  
Clinical Diagnoses ◽  
Significant Performance ◽  
Clinically Significant ◽  
Age Range

Background Early detection of childhood developmental delays is very important for the treatment of disabilities. Objective To investigate the possibility of detecting childhood developmental delays leading to disabilities before clinical registration by analyzing big data from a health insurance database. Methods In this study, the data from children, individuals aged up to 13 years (n=2412), from the Sample Cohort 2.0 DB of the Korea National Health Insurance Service were organized by age range. Using 6 categories (having no disability, having a physical disability, having a brain lesion, having a visual impairment, having a hearing impairment, and having other conditions), features were selected in the order of importance with a tree-based model. We used multiple classification algorithms to find the best model for each age range. The earliest age range with clinically significant performance showed the age at which conditions can be detected early. Results The disability detection model showed that it was possible to detect disabilities with significant accuracy even at the age of 4 years, about a year earlier than the mean diagnostic age of 4.99 years. Conclusions Using big data analysis, we discovered the possibility of detecting disabilities earlier than clinical diagnoses, which would allow us to take appropriate action to prevent disabilities.

scholarly journals Characteristics of Osteoporosis & Osteoporotic Fractures in Korea Based on Health Insurance Review and Assessment (HIRA) Database: 2009–2017

Healthcare ◽  
2021 ◽  
Vol 9 (3) ◽  
pp. 324
Author(s):  
Ho-Seok Oh ◽  
Sung-Kyu Kim ◽  
Hyoung-Yeon Seo
Keyword(s):  
Health Insurance ◽  
Age Groups ◽  
Osteoporotic Fractures ◽  
Prescription Data ◽  
Diagnostic Codes ◽  
Number Of Patients ◽  
Upper And Lower Extremities ◽  
Fractures Of The Spine ◽  
And Gender ◽  
Age Range

To investigate the incidence and characteristics of osteoporosis and osteoporotic fractures in Korea, we used the Health Insurance Review and Assessment Service (HIRA) database. Patients over 50 years old, who were diagnosed or treated for osteoporosis and osteoporotic fractures in all hospitals and clinics, were analyzed between 1 January 2009 and 31 December 2017 by using the HIRA database that contains prescription data and diagnostic codes. These data were retrospectively analyzed by decade and age-specific and gender-specific incidents in each year. We also evaluated other characteristics of patients including medication state of osteoporosis, primary used medical institution, regional-specific incidence of osteoporosis, and incidence of site-specific osteoporotic fractures. The number of osteoporosis patients over 50 years old, as diagnosed by a doctor, steadily increased from 2009 to 2017. The number of osteoporosis patients was notably greatest in the 60′s and 70′s age groups in every study period. Patients undergoing treatment for osteoporosis increased significantly (96%) from 2009 to 2017. Among the patients diagnosed with osteoporosis, the proportion who experienced osteoporotic fracture increased gradually (60%) from 2009 to 2017. The number of patients with osteoporotic fractures of the spine and hip was highest in the 70 to 90 age range, and the number of patients with osteoporotic fractures in the upper and lower extremities was highest in the 50 to 70 age range. Understanding the trends of osteoporosis in Korea will contribute to manage the increased number of patients with osteoporosis and osteoporotic fractures.

Health Insurance Status as a Predictor of Mode of Colon Cancer Detection but Not Stage at Diagnosis: Implications for Early Detection

2021 ◽  
pp. 003335492199917
Author(s):  
Lindsey A. Jones ◽  
Katherine C. Brewer ◽  
Leslie R. Carnahan ◽  
Jennifer A. Parsons ◽  
Blase N. Polite ◽  
...  
Keyword(s):  
Colon Cancer ◽  
Health Insurance ◽  
Early Detection ◽  
Late Stage ◽  
Early Stage ◽  
Insurance Status ◽  
Stage At Diagnosis ◽  
Health Insurance Status ◽  
Percentage Point Increase ◽  
Point Increase

Objective For colon cancer patients, one goal of health insurance is to improve access to screening that leads to early detection, early-stage diagnosis, and polyp removal, all of which results in easier treatment and better outcomes. We examined associations among health insurance status, mode of detection (screen detection vs symptomatic presentation), and stage at diagnosis (early vs late) in a diverse sample of patients recently diagnosed with colon cancer from the Chicago metropolitan area. Methods Data came from the Colon Cancer Patterns of Care in Chicago study of racial and socioeconomic disparities in colon cancer screening, diagnosis, and care. We collected data from the medical records of non-Hispanic Black and non-Hispanic White patients aged ≥50 and diagnosed with colon cancer from October 2010 through January 2014 (N = 348). We used logistic regression with marginal standardization to model associations between health insurance status and study outcomes. Results After adjusting for age, race, sex, and socioeconomic status, being continuously insured 5 years before diagnosis and through diagnosis was associated with a 20 (95% CI, 8-33) percentage-point increase in prevalence of screen detection. Screen detection in turn was associated with a 15 (95% CI, 3-27) percentage-point increase in early-stage diagnosis; however, nearly half (47%; n = 54) of the 114 screen-detected patients were still diagnosed at late stage (stage 3 or 4). Health insurance status was not associated with earlier stage at diagnosis. Conclusions For health insurance to effectively shift stage at diagnosis, stronger associations are needed between health insurance and screening-related detection; between screening-related detection and early stage at diagnosis; or both. Findings also highlight the need to better understand factors contributing to late-stage colon cancer diagnosis despite screen detection.

Early detection of diabetic retinopathy from big data in hadoop framework

Displays ◽  
2021 ◽  
Vol 70 ◽  
pp. 102061
Author(s):  
Amartya Hatua ◽  
Badri Narayan Subudhi ◽  
Veerakumar T. ◽  
Ashish Ghosh
Keyword(s):  
Big Data ◽  
Diabetic Retinopathy ◽  
Early Detection ◽  
Hadoop Framework

Diagnostic value of susceptibility-weighted imaging for endometrioma: preliminary results from a retrospective analysis

2021 ◽  
pp. 028418512110224
Author(s):  
Hong Chen ◽  
Guoliang Wang ◽  
Xuexue Wang ◽  
Yan Gao ◽  
Junhua Liang ◽  
...  
Keyword(s):  
Cyst Wall ◽  
Preoperative Diagnosis ◽  
Final Analysis ◽  
Diagnostic Value ◽  
Susceptibility Weighted Imaging ◽  
Hemorrhagic Disease ◽  
Presenting Symptoms ◽  
Clinical Diagnoses ◽  
Magnetic Resonance Imaging Mri ◽  
Age Range

Background Endometrioma is a common manifestation of endometriosis that can be difficult to diagnose with conventional magnetic resonance imaging (MRI). Susceptibility-weighted imaging (SWI) may be more sensitive than conventional MRI in the detection of chronic, local hemorrhagic disease. Purpose To investigate whether signal voids in SWI sequences could be used in the preoperative diagnosis of endometrioma. Material and Methods This retrospective study included consecutive female patients with clinically suspected endometrioma. All patients underwent pelvic 3-T MRI (T1- and T2-weighted) and SWI within two weeks before laparoscopy. Two experienced radiologists blinded to the histopathologic/clinical diagnoses interpreted the images together, and any disagreements were resolved by consensus. Results The final analysis included 73 patients: 46 patients (mean age=37 years; age range=22–68 years) with 85 endometrioma lesions and 27 patients (mean age=34 years; age range=15–68 years) with 34 non-endometrioid cystic lesions (18 hemorrhagic corpus luteal cysts, three simple cysts, three mucinous cystadenomas, two mature teratomas, and one endometrioid cyst with corpus luteum rupture/hemorrhage). The presenting symptoms for patients with endometrioma were chronic pelvic pain (44.6%), dysmenorrhea (31.9%), infertility (12.8%), dyspareunia (6.4%), and menstrual irregularity (4.3%). MRI identified all 119 lesions observed laparoscopically. SWI visualized punctate or curvilinear signal voids along the cyst wall or within the lesion in 67 of 85 endometriomas (78.8%) and only 3 of 31 non-endometrioid cysts (8.8%). Conclusion The use of SWI to look for signal voids in the cyst wall or within the lesion could facilitate the preoperative diagnosis of endometrioma.

Sign in / Sign up

Export Citation Format

Share Document